{"id":"https://openalex.org/W1932372388","doi":"https://doi.org/10.1109/ssdm.2003.1214944","title":"Approximate string joins","display_name":"Approximate string joins","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W1932372388","doi":"https://doi.org/10.1109/ssdm.2003.1214944","mag":"1932372388"},"language":"en","primary_location":{"id":"doi:10.1109/ssdm.2003.1214944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssdm.2003.1214944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"15th International Conference on Scientific and Statistical Database Management, 2003.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Srivastava","raw_affiliation_strings":["AT and T Research Laboratories, USA","AT/spl and/T Labs-Res., Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT/spl and/T Labs-Res., Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088315797"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12692731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.9023756384849548},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7663258910179138},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.765235960483551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576330900192261},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.649787187576294},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5104628801345825},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5063611268997192},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4693770408630371},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44195663928985596},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4416015148162842},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.4282018840312958},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.24006369709968567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20383688807487488},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.1975395381450653},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19507846236228943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1355321705341339}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9023756384849548},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7663258910179138},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.765235960483551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576330900192261},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.649787187576294},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5104628801345825},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5063611268997192},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4693770408630371},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44195663928985596},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4416015148162842},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.4282018840312958},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.24006369709968567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20383688807487488},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.1975395381450653},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19507846236228943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1355321705341339},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssdm.2003.1214944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssdm.2003.1214944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"15th International Conference on Scientific and Statistical Database Management, 2003.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W112142966","https://openalex.org/W1647671624","https://openalex.org/W2116544254","https://openalex.org/W2144211451","https://openalex.org/W2161936973"],"related_works":["https://openalex.org/W2950268498","https://openalex.org/W1505906253","https://openalex.org/W2298909997","https://openalex.org/W2102443632","https://openalex.org/W4386026606","https://openalex.org/W2154800282","https://openalex.org/W2073112656","https://openalex.org/W1995433548","https://openalex.org/W2756522268","https://openalex.org/W3154492635"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"String":[4],"data":[5],"is":[6,9,24,62],"ubiquitous":[7],"and":[8,43,60,92,99],"commonly":[10],"used":[11],"to":[12,25,65,103],"correlate":[13],"(or":[14],"join)":[15],"entities":[16],"across":[17],"autonomous,":[18],"heterogeneous":[19],"databases.":[20],"The":[21,70],"main":[22],"challenge":[23,64],"effectively":[26],"deal":[27],"with":[28],"the":[29],"noisy":[30],"nature":[31],"of":[32,83,89],"string":[33,48,57,77,84],"data,":[34],"due":[35],"to,":[36],"for":[37,46,74],"example,":[38],"transcription":[39],"errors,":[40],"incomplete":[41],"information,":[42],"multiple":[44],"conventions":[45],"recording":[47],"value":[49],"attributes.":[50],"Commercial":[51],"databases":[52],"do":[53],"not":[54],"support":[55],"approximate":[56,76],"joins":[58],"directly,":[59],"it":[61],"a":[63,81,107],"implement":[66],"this":[67],"functionality":[68],"efficiently.":[69],"author":[71],"presents":[72],"techniques":[73,96],"performing":[75],"joins,":[78],"based":[79],"n":[80],"variety":[82],"similarity":[85],"metrics,":[86],"including":[87],"variants":[88],"edit":[90],"distance":[91],"cosine":[93],"similarity.":[94],"These":[95],"are":[97],"scalable,":[98],"can":[100],"be":[101],"formulated":[102],"execute":[104],"efficiently":[105],"in":[106],"relational":[108],"database":[109],"management":[110],"system.":[111]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}